SVRMamba: Slice-to-Volume Reconstruction from Multiple MRI Stacks with Slice Sequence Guided Mamba
Open Access
- 11 April 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (8) , 8404-8412
Abstract
In fetal magnetic resonance imaging (MRI), slice-to-volume reconstruction (SVR) involves the computational creation of a 3D volume from multiple stacks of 2D slices. This process is challenging due to slice misalignment and image noise. Current state-of-the-art (SOTA) SVR methods typically employ coarse-to-fine techniques that iteratively refine slice-to-volume motion correction and 3D volume reconstruction. However, both processes are inherently inefficient, making these methods time-consuming and prone to errors. This often results in less robust and accurate outcomes, primarily due to insufficient modeling of the spatial relationships between slices. Typically, 2D fetal MRI slices are acquired using the interleave sequence, which first acquires the odd slices and then the even slices in one stack. To this end, we propose a novel Mamba-based framework called SVRMamba, which integrates slice-to-volume reconstruction with slice sequence-guided state space modeling. Specifically, our approach reformulates Mamba’s unidirectional scanning into a slice sequence-guided odd-even directional scanning method and marks the slice positions using sequence embedding tokens. This enables the network to learn the slice relationships and spatial sequences, enhancing fetal MRI SVR motion correction performance. We further integrate a convolutional neural network (CNN)-based interpolation network that generates a noise-suppressed 3D reconstruction by leveraging the predicted motion for each slice. This framework notably enhances 3D fetal brain SVR, delivering substantial improvements in both reconstruction speed and overall performance. Extensive experiments conducted on various benchmark and clinical datasets demonstrate that SVRMamba significantly outperforms existing SOTA methods, delivering comparable results with a remarkable sixtyfold increase in reconstruction speed.Keywords
This publication has 26 references indexed in Scilit:
- Video Mamba Suite: State Space Model as a Versatile Alternative for Video UnderstandingInternational Journal of Computer Vision, 2025
- VideoMamba: State Space Model for Efficient Video Understanding2024
- Fetal brain tissue annotation and segmentation challenge resultsMedical Image Analysis, 2023
- Age-specific structural fetal brain atlases construction and cortical development quantification for chinese populationNeuroImage, 2021
- Fetal body MRI and its application to fetal and neonatal treatment: an illustrative reviewThe Lancet Child & Adolescent Health, 2021
- Infant FreeSurfer: An automated segmentation and surface extraction pipeline for T1-weighted neuroimaging data of infants 0–2 yearsNeuroImage, 2020
- An automated framework for localization, segmentation and super-resolution reconstruction of fetal brain MRINeuroImage, 2020
- An efficient total variation algorithm for super-resolution in fetal brain MRI with adaptive regularizationNeuroImage, 2015
- Reconstruction of fetal brain MRI with intensity matching and complete outlier removalMedical Image Analysis, 2012
- Registration-Based Approach for Reconstruction of High-Resolution In Utero Fetal MR Brain ImagesAcademic Radiology, 2006